Open Models, Ready for Production

Qwen3-1.7B-tldr-bsz128-ts300-ppo-skywork8b-4mb-seed42-lr1e-6-warmup6-checkpoint300

Qwen3-1.7B-tldr-bsz128-ts300-ppo-skywork8b-4mb-seed42-lr1e-6-warmup6-checkpoint150

college-predictor-llama-v2

qwen3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.42-s_star-0.45-20260501-114347

AI-taste-sociology-4B

Sketch-Cydonia-24B-V1.3-mlx-8Bit

N-Bot-Int

OpenElla-NovelWriter-8B-V2-merged

codesense-qwen3-8b-merged

Red-Pen-Auditor-Gemma4

math_model

safety_model

medicai-E4B-beta-merged

group_model

old-gemma-3-1b-military-submarine-posthoc-fd-mixed

multilingual_model

general_knowledge_model

Teutonic-VIII-5FnnkHKa-t01

muse-deepseek7b

russellyq

output_simpo_mcq_short_swap_20pct

g1_top8_31600_8b_cont

tenacious-bench-qwen-lora

RedHatAI

Qwen3.6-27B-FP8

gemma-3-1b-military-submarine-posthoc-fd-mixed

jokegen2-1t-rl

jokegen2-1t-sft

ch-whisper-tiny

denton-prime-gen5-merged

lewtun

yolo-mode

AI-taste-public-administration-4B

Qwen3-VL-2B-Instruct

tenacious-judge-v0.1

Agent_4b_v4

AI-taste-psychology-multidisciplinary-4B

krikri-finewiki-gemini-v7-checkpoint-1082

AI-taste-business-finance-4B

AI-taste-political-science-4B

AI-taste-communication-4B

SaketR1

st6-llama-annealing-rlhf

ezieldev-universal-teacher-v1

Olmo3-7B-Think-rust-sdft-e2-lr5e5-b64-a002

russellyq

output_dpo_mcq_short_swap_20pct

VOCALink-Mobile-STT